Instructions to use microsoft/git-base-coco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/git-base-coco with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="microsoft/git-base-coco")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("microsoft/git-base-coco") model = AutoModelForImageTextToText.from_pretrained("microsoft/git-base-coco") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
- vision
|
| 6 |
- image-to-text
|
| 7 |
model_name: microsoft/git-base-coco
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# GIT (GenerativeImage2Text), base-sized, fine-tuned on COCO
|
|
@@ -63,4 +64,4 @@ During validation, one resizes the shorter edge of each image, after which cente
|
|
| 63 |
|
| 64 |
## Evaluation results
|
| 65 |
|
| 66 |
-
For evaluation results, we refer readers to the [paper](https://arxiv.org/abs/2205.14100).
|
|
|
|
| 5 |
- vision
|
| 6 |
- image-to-text
|
| 7 |
model_name: microsoft/git-base-coco
|
| 8 |
+
pipeline_tag: image-to-text
|
| 9 |
---
|
| 10 |
|
| 11 |
# GIT (GenerativeImage2Text), base-sized, fine-tuned on COCO
|
|
|
|
| 64 |
|
| 65 |
## Evaluation results
|
| 66 |
|
| 67 |
+
For evaluation results, we refer readers to the [paper](https://arxiv.org/abs/2205.14100).
|